Abstract
How can we transfer the knowledge from a source domain to a target domain when each side cannot observe the data in the other side? Recent transfer learning methods show significant performance in classification tasks by leveraging both source and target data simultaneously at training time. However, leveraging both source and target data simultaneously is often impossible due to privacy reasons. In this paper, we define the problem of unsupervised domain adaptation under blind constraint, where each of the source and the target domains cannot observe the data in the other domain, but data from both domains are used for training. We propose TAN (Transfer Alignment Network for Blind Domain Adaptation), an effective method for the problem by aligning source and target domain features in the blind setting. TAN maps the target feature into source feature space so that the classifier learned from the labeled data in the source domain is readily used in the target domain. Extensive experiments show that TAN (1) provides the state-of-the-art accuracy for blind domain adaptation outperforming the standard supervised learning by up to 9.0% and (2) performs well regardless of the proportion of target domain data in the training data.
Similar content being viewed by others
Notes
References
Aytar Y, Zisserman A (2011) Tabula rasa: Model transfer for object category detection. In: International Conference on Computer Vision, IEEE, pp 2252–2259
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1–2):151–175
Bengio Y (2012) Deep learning of representations for unsupervised and transfer learning. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning, pp 17–36
Bengio Y et al (2009) Learning deep architectures for ai. Foundations and trends. Machine Learning 2(1):1–127
Bousmalis K, Trigeorgis G, Silberman N, Krishnan D, Erhan D (2016) Domain separation networks. In: Advances in Neural Information Processing Systems, pp 343–351
Cao Y, Long M, Wang J (2018) Unsupervised domain adaptation with distribution matching machines. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, pp 2795–2802
Chen M, Weinberger KQ, Blitzer J (2011) Co-training for domain adaptation. In: Advances in Neural Information Processing Systems, pp 2456–2464
Chen M, Xu Z, Weinberger KQ, Sha F (2012) Marginalized denoising autoencoders for domain adaptation. In: Proceedings of the 29th International Coference on International Conference on Machine Learning, Omnipress, pp 1627–1634
Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537
Dai Z, Yang Z, Yang F, Cohen WW, Salakhutdinov RR (2017) Good semi-supervised learning that requires a bad gan. In: Advances in Neural Information Processing Systems, pp 6513–6523
Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11:625–660
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp 1180–1189
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(1):2030–2096
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 580–587
Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th International Conference on Machine Learning, pp 513–520
Jeon H, Lee S, Kang U (2021) Unsupervised multi-source domain adaptation with no observable source data. PLOS ONE 16(7):1–16. https://doi.org/10.1371/journal.pone.0253415
Khamis S, Lampert CH (2014) Coconut: Co-classification with output space regularization. In: BMVC
Kumar A, Sattigeri P, Fletcher T (2017) Semi-supervised learning with gans: Manifold invariance with improved inference. In: Advances in Neural Information Processing Systems, pp 5540–5550
Lampert CH (2014) Blind domain adaptation: An RKHS approach. CoRR arXiv:1406.5362
Lee DH (2013) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol 3, p 2
Lee S, Jeon H, Kang U (2021) Multi-epl: Accurate multi-source domain adaptation. PLOS ONE 16(8):1–15. https://doi.org/10.1371/journal.pone.0255754
Long J, Shelhamer E, Darrell T (2015a) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol 3, p 2
Long M, Cao Y, Wang J, Jordan M (2015b) Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp 97–105
Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp 136–144
Long M, Zhu H, Wang J, Jordan MI (2017) Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp 136–144
Long M, Cao Z, Wang J, Jordan MI (2018) Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, pp 1647–1657
Ma F, Meng D, Xie Q, Li Z, Dong X (2017) Self-paced co-training. In: International Conference on Machine Learning, pp 2275–2284
Miyato T, Maeda Si, Koyama M, Ishii S (2017) Virtual adversarial training: a regularization method for supervised and semi-supervised learning. arXiv preprint arXiv:1704.03976
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp 91–99
Rohrbach M, Ebert S, Schiele B (2013) Transfer learning in a transductive setting. In: Advances in Neural Information Processing Systems, pp 46–54
Saito K, Ushiku Y, Harada T (2017) Asymmetric tri-training for unsupervised domain adaptation. arXiv preprint arXiv:1702.08400
Santos CNd, Wadhawan K, Zhou B (2017) Learning loss functions for semi-supervised learning via discriminative adversarial networks. arXiv preprint arXiv:1707.02198
Sener O, Song HO, Saxena A, Savarese S (2016) Learning transferrable representations for unsupervised domain adaptation. In: Advances in Neural Information Processing Systems, pp 2110–2118
Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229
Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) Cnn features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 806–813
Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474
Tzeng E, Hoffman J, Darrell T, Saenko K (2015) Simultaneous deep transfer across domains and tasks. In: International Conference on Computer Vision (ICCV), IEEE, pp 4068–4076
Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Computer Vision and Pattern Recognition (CVPR), vol 1, p 4
Uzair M, Mian AS (2017) Blind domain adaptation with augmented extreme learning machine features. IEEE Trans Cybern 47(3):651–660
Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3(1):9
Xiao M, Guo Y (2013) Domain adaptation for sequence labeling tasks with a probabilistic language adaptation model. In: Proceedings of the 30th International Conference on International Conference on Machine Learning, JMLR. org, pp I–293
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp 3320–3328
Zhang X, Yu FX, Chang SF, Wang S (2015) Deep transfer network: Unsupervised domain adaptation. arXiv preprint arXiv:1503.00591
Acknowledgements
This work was supported in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2020-0-00894, Flexible and Efficient Model Compression Method for Various Applications and Environments) and in part by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0-01343, Artificial Intelligence Graduate School Program (Seoul National University)). The Institute of Engineering Research at Seoul National University provided research facilities for this work. The ICT at Seoul National University provides research facilities for this study. U Kang is the corresponding author.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, H., Kang, U. Transfer alignment network for blind unsupervised domain adaptation. Knowl Inf Syst 63, 2861–2881 (2021). https://doi.org/10.1007/s10115-021-01608-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-021-01608-x